Abnormal vein image restoration method and device
A vein image and repair method technology, which is applied in the field of abnormal vein image repair methods and devices, and can solve the problems of poor removal of abnormal areas of vein images, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0077] The internal area of a normal finger vein image can be divided into a background area and a vein area. The background area is an area with a high gray value, and the vein area is an area with a low gray value. Both belong to the normal area of the finger vein image. The abnormal finger vein image also contains abnormal areas. The common abnormal areas are that in the process of finger vein image acquisition, foreign objects appearing in the acquisition window or attached to the finger block the light source, or the hardware failure of the acquisition equipment results in abnormal areas in the finger vein image. The regions with low gray values are shown in the The blood in the veins of fingers only has a strong absorption of near-infrared light, and the light source of the collection equipment also has natural light in addition to near-infrared light, so the gray value of the vein area is relatively low, and after foreign objects block the light source, due to The...
Embodiment 2
[0126] Refer to attached Figure 7 As shown, the present invention also relates to a device for repairing abnormal vein images, which includes:
[0127] 1) Abnormal area screening and processing module, which divides the finger vein image into several segments according to the gradient in the horizontal and vertical directions, and according to the starting point, ending point, average gray value of each segment and the corresponding entire row Or the difference of the gray value of the whole column judges the abnormal area, and expands the abnormal area; the abnormal area screening and processing module is used to realize the function of step 1) of embodiment 1.
[0128] 2) The direction filtering module, which performs direction filtering to determine the direction information of each point in the normal area for the normal area except the abnormal area; the direction filtering template is used to realize the function of step 2) of the first embodiment.
[0129] 3) The best...
experiment example
[0133] The effectiveness of the method for repairing abnormal veins involved in the present invention is verified by comparing the recognition rates before and after repairing the abnormal image database.
[0134] First, a normal image / finger is collected as a registration image, and a total of 500 fingers are collected. Then collect the abnormal images of these 500 fingers. The method is to stick a small piece of paper on the finger of the person to be collected during the collection, and collect 10 abnormal images for each finger as a verification image. For comparison, the simulation and recognition rate comparisons are also made with the commonly used image denoising algorithms median filter and mean filter.
[0135]The comparison adopts a 1:N comparison method, that is, 1:500, and there are a total of 5,000 comparison results, which are divided into a comparison success rate test and a comparison recognition false rate test. The comparison success rate test is that when ...
PUM
![No PUM](https://static-eureka-patsnap-com.libproxy1.nus.edu.sg/ssr/23.2.0/_nuxt/noPUMSmall.5c5f49c7.png)
Abstract
Description
Claims
Application Information
![application no application](https://static-eureka-patsnap-com.libproxy1.nus.edu.sg/ssr/23.2.0/_nuxt/application.06fe782c.png)
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap